---
title: "GPT Image 2 API — All variants, pricing, code samples | RunAPI"
url: "https://runapi.ai/models/gpt-image-2.md"
canonical: "https://runapi.ai/models/gpt-image-2.md"
locale: "en"
model: "GPT Image 2"
provider: "OpenAI"
modality: "image"
variant_count: 2
price_from_cents: 24
---

# GPT Image 2

Latest OpenAI image generation with near-perfect multilingual text rendering inside images.

**Provider:** OpenAI
**Modality:** Image
**Catalog:** 2 variants

GPT Image 2 is OpenAI's latest image generation model featuring near-perfect multilingual text rendering within generated images. It improves on instruction following and fine-grained visual detail over its predecessor.

## Variants

| Version | Variant | Pricing | Billing | URL |
|---|---|---|---|---|
| gpt-image-2-image-to-image | `image-to-image` | $0.240 | call | https://runapi.ai/models/gpt-image-2/image-to-image.md |
| gpt-image-2-text-to-image | `text-to-image` | $0.240 | call | https://runapi.ai/models/gpt-image-2/text-to-image.md |


## Install

```sh
npm install @runapi.ai/gpt-image-2
# or
gem install runapi-gpt_image_2
```

## Quickstart

```sh
curl -X POST https://runapi.ai/api/v1/gpt_image_2/edit_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "gpt-image-2-image-to-image", "prompt": "..." }'
```

## Context

GPT Image 2 is OpenAI's newest image model, notable for near-perfect multilingual text rendering. Through RunAPI, both text-to-image and image-to-image endpoints share one key.

## FAQ

### Which variant should I start with?

Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.

### Is there a free tier?

New accounts get free first calls on every model. After that, pay per call.

### Do you stream results?

Where streaming is available, RunAPI streams end-to-end.

### How are failures billed?

Failed generations are not charged.

### Are outputs cached?

Generated outputs are stored and retrievable by task ID. Inputs are not cached.

### Can I use commercially?

Yes — commercial use is included for every variant unless a model license explicitly restricts it, which is called out on the variant page.

### What about rate limits?

Per-key rate limits scale with usage tier. See pricing page for current limits.

### Where can I report issues?

Open an issue on the public GitHub repo or email support.